Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification

TL;DR

Con4m introduces a context-aware consistency learning framework that leverages temporal and label context to improve segmented time series classification, especially under varying class durations and label inconsistencies.

Contribution

The paper proposes Con4m, a novel framework that utilizes contextual priors and consistency learning to enhance segmented TSC performance amidst label noise and class duration variability.

Findings

Con4m outperforms existing models on multiple datasets.

It effectively handles label inconsistencies and class duration variations.

Experimental results demonstrate significant accuracy improvements.

Abstract

Time Series Classification (TSC) encompasses two settings: classifying entire sequences or classifying segmented subsequences. The raw time series for segmented TSC usually contain Multiple classes with Varying Duration of each class (MVD). Therefore, the characteristics of MVD pose unique challenges for segmented TSC, yet have been largely overlooked by existing works. Specifically, there exists a natural temporal dependency between consecutive instances (segments) to be classified within MVD. However, mainstream TSC models rely on the assumption of independent and identically distributed (i.i.d.), focusing on independently modeling each segment. Additionally, annotators with varying expertise may provide inconsistent boundary labels, leading to unstable performance of noise-free TSC models. To address these challenges, we first formally demonstrate that valuable contextual information enhances the discriminative power of classification instances. Leveraging the contextual priors of MVD at both the data and label levels, we propose a novel consistency learning framework Con4m, which effectively utilizes contextual information more conducive to discriminating consecutive segments in segmented TSC tasks, while harmonizing inconsistent boundary labels for training. Extensive experiments across multiple datasets validate the effectiveness of Con4m in handling segmented TSC tasks on MVD. The source code is available at https://github.com/MrNobodyCali/Con4m.